System, method, and software application for targeted advertising via behavioral model clustering, and preference programming based on behavioral model clusters

Abstract

The method and system for TV user profile data prediction and modeling allows accurate and narrowly focused behavioral clustering. A client-side system classifies television consumers into representative user profiles. The profiles target individual user advertising and program preference category groups. A contextual behavioral profiling system determines the user's monitor behavior and content preferences, and the system may be continually updated with user information. A behavioral model database is queried by various system modules. The programming, including targeted advertising for television and interactive television is based on the profile data prediction, modeling and preference determination. The system is enabled to present a complete program sequence to the viewer based on the preference determination and stored programming. The latter is referred to as automatic program sequence (virtual channel) creation and the virtual channel can be presented as a separate channel in an electronic programming guide (EPG).

Description

CROSS-REFERENCE TO RELATED APPLICATIONS[0001]This application claims the benefit under 35 U.S.C. 119 (e) of provisional application No. 60 / 260,745, filed Jan. 9, 2001 and further benefits of priority under 35 U.S.C. 120 for non-provisional application Ser. No. 10 / 043,171 filed on Jan. 9, 2002.[0002]Further reference is had to the disclosures found in the commonly assigned, concurrently filed, copending patent application Ser. No. 10 / 043,698; application Ser. No. 09 / 893,192, describing a system and method for delivery of television programs and targeted de-coupled advertising; application Ser. No. 09 / 096,592 entitled “Television Program Recording with User Preference Determination;” and application Ser. No. 09 / 953,327, describing logic operators for delivery of targeted programming, and SQL query operators for targeting expressions. The disclosures of the copending applications are herewith incorporated by reference.BACKGROUND OF THE INVENTION[0003]1. Field of the Invention[0004]The ...

AI Technical Summary

Benefits of technology

The invention provides a system and method for behavioral model clustering in TV usage and targeted program delivery, as well as an advertisement manager and a preference engine for interactive display systems. The system includes a clustering engine that receives television viewing data and program content metadata, and a demographic cluster knowledge base acquirer that predicts demographic groups of users based on their behavioral data. The system uses these models to determine which advertisements to target and which program content to display to users. The invention aims to improve the effectiveness of advertisements and enhance user experience by learning from their behavior and preferences.

Problems solved by technology

Since prior art systems do not model transitions, sequential program behavior, and temporal program utilization in a general predictive architecture, they are unable to predict a user's preference based on sophisticated content and temporal relationships.

By not assessing when there is adequate evidence to infer a preference, known methods tend to incorrectly predict user preferences, or they may wait too long before building higher confidence.

However, this is inaccurate as the data are not generally subject to normal distribution.

In the context of program or advertising program preference determination, the prior art methods do not have an automatic user input, and thus no method of learning which metrics best predict a certain user's preference.

This reduces targeting performance in non-demographically classifiable consumer groups, and demographic inferring accuracy.

Images